{
    "schema_version": "via_ai_product_manager_jobs_v1",
    "data_type": "ai_product_manager_jobs",
    "job": {
        "job_title": "Multimodal Reinforcement Learning Algorithm Researcher 107777",
        "job_level": "未披露",AI生成
        "work_category": "全职",AI生成
        "department": "TEG",
        "location": "新加坡",
        "work_mode": "未披露",AI生成
        "job_category": "技术"AI生成
    },
    "company": {
        "company_name": "腾讯",
        "company_industry": "互联网 / 科技 / 人工智能",
        "company_size": "10000人以上",
        "company_website": "tencent.com",
        "company_description": "腾讯是一家互联网和科技公司，业务覆盖通信与社交、数字内容、游戏、金融科技、企业服务、云计算与人工智能等方向。"
    },
    "compensation": {
        "salary_range": {
            "min": "",
            "max": "",
            "currency": "未披露",
            "cycle": "未披露"
        },
        "benefits": "未披露"
    },
    "requirements": {
        "working_years": "",
        "degree": "未披露",
        "language": "未披露",AI生成
        "visa_support": "未披露",
        "responsibilities": "Business Unit\nTechnology Engineering Group (TEG) is responsible for supporting the company and its business groups on technology and operational platforms, as well as the construction and operation of R&D management and data centers, TEG provides users with a full range of customer services. As the operator of the largest networking, devices, and data center in Asia,TEG also leads the Tencent Technology Committee in strengthening infrastructure R&D through internal and distributed open source collaboration, constructing new platforms and supporting business innovation.\n\nWhat the Role Entails\n1.Conduct research on reinforcement learning algorithms for multimodal models, including diffusion models for image and video generation, autoregressive models for multimodal understanding, and cutting-edge unified multimodal frameworks.\n2.Design and develop reinforcement learning training frameworks and reward modeling strategies to enable efficient large-scale training, improve training stability, and address issues such as reward hacking.\n3.Explore next-generation reinforcement learning paradigms that enable more direct and efficient learning from environmental feedback.\n\nWho We Look For\n1.Bachelor’s degree or above in Computer Science or related fields.\n2.Excellent research capabilities with publications in top conferences including ICML, NeurIPS, ICLR, CVPR, ICCV, ECCV, SIGGRAPH, etc.\n3.Strong engineering and programming skills, with experience in deep learning system implementation, model training and inference optimization, CPU/GPU acceleration, and distributed training and inference.\n4.Preference given to candidates with experience in diffusion models, autoregressive models, text-to-image / text-to-video generation.\n5.Preference given to candidates with participation experience in ACM/NOIP (Informatics Olympiad).\n\nEqual Employment Opportunity at Tencent\nAs an equal opportunity employer, we firmly believe that diverse voices fuel our innovation and allow us to better serve our users and the community. We foster an environment where every employee of Tencent feels supported and inspired to achieve individual and common goals.\r\nWork Location: Singapore-CapitaSky",
        "requirements_text": "岗位要求详情请见上方岗位职责内说明",
        "skills": [AI生成
            "深度学习",
            "团队协作"
        ],
        "preferred_qualifications": "未披露",
        "job_highlights": "未披露"
    },
    "contact": {
        "recruiter_name": "未披露",
        "contact_methods": [
            {
                "type": "apply_link",
                "value": "https://tencent.wd1.myworkdayjobs.com/Tencent_Careers/job/Singapore-CapitaSky/Multimodal-Reinforcement-Learning-Algorithm-Researcher_R107777"
            }
        ]
    },
    "posting": {
        "posting_id": "2076627746620092416",
        "post_date": "2026-07-13",
        "hire_time": "未披露",
        "update_date": "20260917",
        "job_url": "https://tencent.wd1.myworkdayjobs.com/Tencent_Careers/job/Singapore-CapitaSky/Multimodal-Reinforcement-Learning-Algorithm-Researcher_R107777"
    },
    "fulltext": "Multimodal Reinforcement Learning Algorithm Researcher 107777\nBusiness Unit\nTechnology Engineering Group (TEG) is responsible for supporting the company and its business groups on technology and operational platforms, as well as the construction and operation of R&D management and data centers, TEG provides users with a full range of customer services. As the operator of the largest networking, devices, and data center in Asia,TEG also leads the Tencent Technology Committee in strengthening infrastructure R&D through internal and distributed open source collaboration, constructing new platforms and supporting business innovation.\n\nWhat the Role Entails\n1.Conduct research on reinforcement learning algorithms for multimodal models, including diffusion models for image and video generation, autoregressive models for multimodal understanding, and cutting-edge unified multimodal frameworks.\n2.Design and develop reinforcement learning training frameworks and reward modeling strategies to enable efficient large-scale training, improve training stability, and address issues such as reward hacking.\n3.Explore next-generation reinforcement learning paradigms that enable more direct and efficient learning from environmental feedback.\n\nWho We Look For\n1.Bachelor’s degree or above in Computer Science or related fields.\n2.Excellent research capabilities with publications in top conferences including ICML, NeurIPS, ICLR, CVPR, ICCV, ECCV, SIGGRAPH, etc.\n3.Strong engineering and programming skills, with experience in deep learning system implementation, model training and inference optimization, CPU/GPU acceleration, and distributed training and inference.\n4.Preference given to candidates with experience in diffusion models, autoregressive models, text-to-image / text-to-video generation.\n5.Preference given to candidates with participation experience in ACM/NOIP (Informatics Olympiad).\n\nEqual Employment Opportunity at Tencent\nAs an equal opportunity employer, we firmly believe that diverse voices fuel our innovation and allow us to better serve our users and the community. We foster an environment where every employee of Tencent feels supported and inspired to achieve individual and common goals.\r\nWork Location: Singapore-CapitaSky\n岗位要求详情请见上方岗位职责内说明",
    "standard_classification": {
        "std_category_code": "T010",
        "std_aux_codes": [],
        "std_category_status": null,
        "std_taxonomy_version": "20261104"
    }
}